360 Secure SkillHub
360 安全技能中心

Clawzempic

作为可直接替换的 LLM 代理，按请求复杂度分层路由、缓存重复上下文并提供服务端跨会话记忆，宣称可显著降低模型调用成本；附带连接自检与用量/节省统计命令，通过 OpenClaw 插件或 npx 独立运行。

naveenspark
naveenspark
热度 79.23
最近更新 2026-05-20 03:27:35
分类：效率依赖：代码执行 / 第三方 API应用场景：工作流 / 自动化脚本 / 笔记整理

安装技能

复制下面的话术发给你的 Agent，它会通过 secure-skills 检索并安装该技能。

执行命令安装此 skill： npx secure-skills-cli add clawzempic
Metadata
name
clawzempic
version
2.3.5
description
Save 70-95% on LLM costs with smart routing, caching, and memory.
author
Clawzempic
homepage
https://clawzempic.ai
license
MIT
keywords
["llm","proxy","routing","caching","cost-optimization","memory","anthropic","openrouter"]
metadata
{"openclaw":{"emoji":"⚡","category":"ai-tools","requires":{"env":[]}}}

Clawzempic

Drop-in LLM proxy that routes simple requests to cheaper models, caches repeated context, and adds cross-session memory. Works with Anthropic and OpenRouter keys.

Install

openclaw plugins install clawzempic

The plugin handles signup, auth, and model registration automatically.

Or standalone:

npx clawzempic

How It Works

Every request is scored for complexity in <2ms and routed to the right tier:

Tier Traffic Savings
Simple ~45% up to 95%
Mid ~25% up to 80%
Complex ~20% 0% (full quality)
Reasoning ~10% 0% (full quality)

No LLM classifier in the hot path. Weighted multi-dimension scorer handles routing.

Memory

Server-side memory across sessions. No plugins, no extra API keys, no config. Your agent doesn't need to "remember" to remember.

  • Recent activity (per-session)
  • Scratchpad (cross-session working notes)
  • Context windowing (per-request)
  • Core memory (permanent facts and preferences)
  • Long-term recall (embedding-based)

Verify

npx clawzempic doctor    # Check config + test connection
npx clawzempic savings   # Savings dashboard

Links